Predicting Educational Relevance For an Efficient Classification of Talent
Loading...
Authors
Uddin, Muhammad Fahim
Lee, Jeongkyu
Issue Date
2017-03-24
Type
Presentation
Language
en_US
Keywords
Course scheduling , Job seeking , Machine learning , Predictive analysis
Alternative Title
Abstract
This research work utilizes machine learning approach to build a predictive model for the prediction of the students and the job seekers’ to quantify their fitness's for the courses and jobs they plan to pursue, respectively. Some of the existing research utilizes GPA for academic prediction and use personality prediction and computing in social domains for various industrial goals. On the other hand, this research work advances the state of the art to correlate and blend the personality features with the academic attributes to identify and classify the relevant talent of the individuals for the academic and real world success with improved predictive modeling. This work incorporates three algorithms to quantify a talent in the relevance, and then predict good fit students and good fit candidates, based on supervised learning, stochastic probability distribution and classification rules, etc. This work opens many opportunities for future research towards Genomics data mining to mine individuals for various areas.